Chatbots Behaving Badly by Markus Brinsa
Chatbots Behaving Badly
Tasteful AI, Revisited.
0:00
-9:38

Tasteful AI, Revisited.

Taste just became a setting. From Midjourney’s Style and Omni References to Spotify’s editable Taste Profile and Apple’s Writing Tools, judgment is moving from vibe to control panel. We unpack the new knobs, the research on “latent persuasion,” why models still struggle to capture your implicit voice, and a practical workflow to build your own private “taste layer” without drifting into beautiful sameness. Sources in show notes.

The episode is based on the article “Tasteful AU, Revisited” by Markus Brinsa.

https://chatbotsbehavingbadly.com/tasteful-ai-revisited-from-style-knobs-to-taste-controls-1

Discussion about this episode

User's avatar